基于螺纹边缘图像的快速SSDA算法  

A Fast SSDA Algorithm Based on Edge Image of Thread

作　　者：郭建成[1] 林菁[1] 

机构地区：[1]上海师范大学数理信息学院,上海200234

出　　处：《计算机与数字工程》2009年第3期72-74,共3页Computer & Digital Engineering

摘　　要：序贯相似性检测算法(SSDA)是针对传统的模板匹配算法提出的一种高效的图像匹配算法,但是SSDA算法难以满足螺纹检测的实时性。针对传统SSDA算法的不足,提出了一种基于螺纹边缘图像的快速SSDA算法。该方法用形态学对螺纹图像进行了边缘提取,然后只在边缘处进行匹配,从而大大减少了匹配的次数,同时提出了减小匹配运算量的方法。The sequential similarity detection algorithm （SSDA） is proposed to improve the conventional image matching, which is an efficient image matching algorithm. But the SSDA algorithm can not meet the real - time of thread detection. For the lack of traditional SSDA algorithm, a fast SSDA algorithm based on the edge image of thread is pro- posed. This method extracts edge points of thread based on morphology, then match on the edge points. This can reduce the number of the match greatly. At the same time, a method is proposed to reduce the computing amount of matching.

关 键 词：螺纹 形态学 边缘提取 图像匹配 SSDA 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]